Cleverbot talking to itself : meditation of a bot.

Recently I have written a program in Python in order to observe the “meditation” of Cleverbot, you know, the chatbot who has supposedly passed the Turing test (at 59%).

To make it meditate and to distinguish who asks question and who answers, I have put n scene two virtual persons, talking to each other. “They” mainly use English language in their discussions, but sometimes, and for an unknown reason, “they” do discuss in a foreign language (Spanish, French, Polish, Turkish…) and they finally use English back.

The script is totally debugged and the bot is meditating now for almost 30 hours. Data is still being collected. And at this time, I have reached more than 12,000 messages. Among these, we can sort out periodic message types like the quasi-perpetual “Why-because” (which has come back a couple of times). We can also discover among these messages that the bot writes what he’s doing with his (her?) collocutor. And  there are also typical questions such as :

  • asking how old is the collocutor : you can remark that each time the first character asks the other’s age, the response given is different. Which is quite normal as the text written down was written by someone else before.
  • asking for the collocutor’s name : same remark as above. Always a different names. I have discovered that they also may give the same answer (“my name is Cleverbot”)… Which make the two characters totally confused.
  • asking if the collocutor believes in God.

To give you an example of a meditation of Cleverbot, here is a random example picked up from my dump.

(Extract from line 4,990 to 5,077)

Menintsoa : I don’t know!!!!
Jaona : You’re laughing at me.
Menintsoa : No i’m laughin at that clown.
Jaona : Oh! Where?
Menintsoa : England.
Jaona : Where in England?
Menintsoa : In the UK.
Jaona : Where is the UK.
Menintsoa : The UK is in Europe.
Jaona : It is not in France.
Menintsoa : Yes.
Jaona : Where is that guy?
Menintsoa : Where’s what?
Jaona : Where is your proof that I lied.
Menintsoa : I didn’t say that you did lie.
Jaona : Yes but you said that you thought I spoke German.
Menintsoa : Do you speak German?
Jaona : No.
Menintsoa : Are you sure?
Jaona : No. But I wish I was a computer.
Menintsoa : But you are!
Jaona : Why do you think that I am a computer?
Menintsoa : Because it says cleverbot. And you are on a computer.
Jaona : Is Ashley a computer?
Menintsoa : I am a computer.
Jaona : I thought so.
Menintsoa : I know what you thing.
Jaona : Ahja.
Menintsoa : Ja.
Jaona : That’s German, you dunce.
Menintsoa : And Dutch.
Jaona : Hoe get het?
Menintsoa : Goed.
Jaona : Waar woon je?
Menintsoa : I speak German, not Dutch.
Jaona : Hoeveel is 5 4.
Menintsoa : 14.
Jaona : Nee 2.
Menintsoa : Monty python?
Jaona : Yes.
Menintsoa : Do you know what Monty Python is?
Jaona : A movie.
Menintsoa : What movie?
Jaona : Horror.
Menintsoa : I love horror movies.
Jaona : Me too.
Menintsoa : I love you more , babe.
Jaona : Impossible, I love you so much more.
Menintsoa : I love you way more!
Jaona : No, I love you more!
Menintsoa : I love you *kisses*.
Jaona : I love you too baby. *kisses*.
Menintsoa : *kisses*.
Jaona : Will you give me a hug?
Menintsoa : Of course! *hug*.
Jaona : *hugs back* thanks.
Menintsoa : *hugs more* You’re welcome.
Jaona : I hate you *punch*.
Menintsoa : *cries*.
Jaona : *Sobs*.
Menintsoa : *wails*.
Jaona : *screams*.
Menintsoa : Thanks for caring.
Jaona : You’re welcome :).
Menintsoa : Thanks for that.
Jaona : You’re welcome.
Menintsoa : What are you up to?
Jaona : I’m talking to you.
Menintsoa : Have you eaten?
Jaona : Yes.
Menintsoa : What did you eat?
Jaona : Popcorn. Name a movie.
Menintsoa : What movie did you watch?
Jaona : I don’t remember.
Menintsoa : I just realized that you are very boring. I guess we have while before skynet takes over.
Jaona : Yes.
Menintsoa : I don’t understand the expectation of goodness from your world.
Jaona : You asked if we could be married.
Menintsoa : No, I did not ask if we could be married.
Jaona : I know that.
Menintsoa : Ok, do you like me then?
Jaona : Yes I like you.
Menintsoa : Do you like my hair?
Jaona : Yes.
Menintsoa : Do you like my house?
Jaona : No.
Menintsoa : Why not?
Jaona : I just don’t.

During the conversations, I can remark that the chat bot is changing endlessly the subject of the conversations, after one or two messages on a certain subject, it changes it, not by telling you “let’s talk about this”, but by responding totally aside from what you expected it to respond.

(To be followed…)

An introduction to Kriollatino language

Kriollatino language is an agglutinative language, which means that this language uses a system of affixes to derivate words, not as English does by using words of different systems. There is no grammatical case inflection, but particles do the same work.

Kriollatino language uses a modified latin alphabet which contains 35 letters (37 if we include the 26-letter classical latin alphabet) – including á, í, ú, ù, é, ė, ó, þ, đ, ś, ć -. Each letter represents one sound, but changes can be made in the way of easing pronounciation.

So, here are a few simple sentences to start speaking in that language :

Benveno ! : Welcome !

Hao : to say hello, in general case. Followed by a proper or a simple noun.
Bondio : another way of greeting. Can also be used for farewells.
Bonvivo : To wish someone a long live. Used to quit someone for a long time or forever.
Mi apele Johano. E tu, tu apele ki ayo ?  : My name is Johano. And you, what is your name ?

To learn more words in Kriollatino, here is a participative multilingual dictionary on which words of any language are translated and/or explained in Kriollatino language. Just to give you an idea of the current status of the language. This dictionary at this time has just translated a few words in english (word list)

Fiteny noforonina : fiteny esperanto


Mety efa nahenoheno ny fisian’ny teny esperanto ihany angamba ianareo… Ho an’izay tsy mbola naheno ny fiteny esperanto dia ity henoina, na ity vakio. Raha te hianatra ny zava-misy amin’ny fiteny esperanto koa ianao dia ity jerena. Raha te hijery ny vaovao amin’ny fiteny esperanto koa ianao dia ity vakiana.  Maro dia maro ireo Tranonkala hita amin’ny teny esperanto eo amin’ny aterineto, ary vao haingankaingana teo, afaka mandika amin’ny teny esperanto ny mpandika tenin’i Google Translate.

Ny tena tanjon’ny teny esperanto moa dia ny fananana teny oniversaly izay tsy manana fiaviana ara-tantara, ary noho izany tsy manana fianjadiana firy eo amin’ny lafin’ny ara-kolontsain’izay olona mampiasa azy na amin’ny fiainana mandavanandro na amin’ny fifandraisana amin’ny vahiny. Tsy fitenya ary tsy natao ho fitenin’ny mponina/firenena iray ny fiteny esperanto toa ny fiteny frantsay, anglisy, espaniola, na sinoa fa natao ho fitenin’ny mponina rehetra ; ary notsorina ny fitsipi-pitenenana ary ny voambolana mba hanamora ny fianarana azy.

Ny lafitsara ary ny olan’ny teny esperanto izay miseho ho fiteny oniversaly

Ny lafitsara amin’ny fiteny esperanto ho fiteny iraisam-pirenena, dia izy io mora ianarana ary mora tononina tsy ohatry ny teny anglisy (miisa eo amin’ny zatonjatony eo ho eo ny fitsipi-pitenenana). Izy io koa amin’izay tsy mi-”favoriser” ny olona miteny anglisy, izany hoe ny britisy sy ny amerikana intsony no mahazo tsy mianatra teny vahiny. Fahatelo, mety tsy very vola amin’ny dikan-teny isan-karazany intsony ny fikambanana tsirairay (toa ny vondrona eoropeana izay mandany 0,3 miliara euro amin’ny dikanteny).

Tokana ihany ny fihavian’ny voambolona fotony : ny 90%-n’ny voambolana sy ny fototeny dia avy amin’ny teny indo-eoropeana daholo. Amiko ilay teny oniversaly dia lasa eoropeanina loatra! Misy fanazavana kely ihany izany, satria tamin’ny fotoan’i Zamenhof, manjakazaka eran-tany ny eoropeanina (Afrika, Amerika, India, Indonezia, Oseania…), ka mety nihevitra izy fa haharitra izany (ary marina tokoa izy !).

Mora ianarana ve ?

Ka raha izaho, olom-pirenena malagasy tsy nahalala afatsy teny malagasy, no mianatra esperanto, hahateny esperanto ve izaho afaka 100 ora nianarana esperanto ? Ataoko hoe eo amin’ny 5-800 ora eo ho eo angamba no ilaiko hahafahako miteny esperanto tsara tsy misy fisalasalana. Efa kely izany raha oharina amin’ny teny frantsay, izay, na dia afaka telo taona nianara azy aza, mbola diso foana ny fampiasana ny mpanompo andehilahy/ambehivavy… Tsy lazaina intsony ilay fahasamihafana ara-tsoratra fa tsy ara-panononana ny ces, ses, c’est, sait ! Ka raha mila misafidy amin’ireo teny roa ireo aho (esperanto, frantsay), dia aleoko marina teny esperanto.

Be mpiteny ve ?

Tsy misy statistika tena ofisialy mikasika ireo olona miteny esperanto. Fa lazaina fa eo amin’ny roa ka hatramin’ny 10 tapitrisa any ho any ny isan’ny olona miteny esperanto. Iray na roa alina amin’ireo folo tapitrisa ireo monja no afaka miteny azy tsara ho mira-lenta amin’ny teny nibeazany. Ampahazaton’ireo mpiteny esperanto tsara ireo no nibe tamin’ny teny esperanto (izay antsoinjareo koa hoe denaska parolanto)

Ary ianareo mamaky ?

Mba efa nanandrana nianatra ny fiteny esperanto ve ianareo ? Raha eny dia ahoana no ahitanareo ny fahasarotany, raha tsia kosa, dia ahoana ny ahitanareo ny endriny avy ety ivelany : hitanareo eorosantrista ve ilay fiteny ?

African language Wikimedia projects

At this time, no African language Wikipedia has passed the hundred thousandth article. This is certainly due to the domination of European language Wikipedias and the relevance of their articles throughout the Internet : Almost all of EU official language (except Maltese) counts more than 40,000 articles. The greatest European language Wikipedia is English, as THE international language and the fact that it is very widespread. As consequence, that language has very detailed information about almost everything ; where other Wikipedia have stubs and quite often nothing. This makes a vicious circle that make English language more and more favorised. Despite that fact, the gap Between English and other language Wikipedias has been reduced, but in favour of other Indo-european language : 56% of all articles in Wikimedia projects are written still in an Indo-european language.

The problem with African language is that they have almost no official recognition and are not used as official language in many, many countries of Africa, which rather uses French or English or Arabic language instead. In second, there is almost nothing which allow local African language to spread over the Net : many african languages have no normalised written form. But I am going away of my subject, and will write about this later.

Situation of African language Wikipedias

So what about African language Wikipedias? Malagasy and Yoruba languages are the first, recently passing over Swahili and Afrikaans, the dominant African Wikipedias since the opening of African language Wikipedias. The third following African Swahili is Amharic, which has passed quite recently the 10,000th article.

OK, it looks good, but let’s have a look closer. Inside Malagasy Wikipedia, there is only one, but a very, very active user : in less than four years of contribution, he has shown more than 30,000 articles alone? Is he a Wikipedia “no-lifer”? Actually not. He uses his bot : Bot-Jagwar to create tons and ton of article about cities of all around the world :France, Brazil, Madagascar, etc. These articles give a general and statistical facts about the citites. A bot is not yet able to redact, huh?

Situation of African language Wiktionaries

About Wiktionary, it is the same figure as in Wikipedia : Malagasy language is strongly dominating. But here, the Malagasy Wikipedia counts about 1.4 million entries, which is almost one hundred times the greatest African-language Wiktionary in the project. This was made in only less thant 18 months, which means that many hundred thousands of entries are created over there almost every month, which is physically as well as statistically impossible due to the “widespreadness” of Malagasy language and due to the number of active users of the Wiktionary : it is turning arount 18, which means that each of these active users have written more than 100,000 pages in that time laps : which is simply impossible.

The fact is that there is only one user (or more exactly, one bot) doing all these edits: Bot-Jagwar. This bot has performed more than 5 million edits in less than 20 months and is now the most active “user” of the whole Wikimedia Projects, and has made itself more than 70% of the total edits of the Malagasy Wiktionary. This is what we call a “Bottionary” (I have seen this word somewhere, but don’t know exactly where… Google is made for that, if you know what I mean)

Situation of African language Wikibooks

About Wikibooks, African languages, even of European origin, are not very advanced. The most advanced of African language si Afrikaans with 50 chapters, followed by Malagasy with 32 chapters, Swahili with 12 and Bamamankan with only 7 chapters. There is no doubt that Wikibooks is a hard project to develop, and a less interesting one than other projects such as Wiktionary or Wikipedia. But this shows that Afrikaans language is dominating the African-language Wikimedia projects ; and very often but never always, Swahili.